Texas Instruments TMS320C67 DSP Series Programmer's Reference Manual page 32

Algorithm
for ( i = 1, j = n2/radix + 1; i < n2 - 1; i++)
{
index[i] = j - 1;
for (k = n2/radix; k*(radix-1) < j; k /= radix)
j -= k*(radix-1);
j += k;
}
index[n2 - 1] = n2 - 1;
}
This is the C equivalent for the assembly code. Note that the assembly code
is hand optimized and restrictions may apply.
void DSPF_sp_bitrev_cplx(double* x, short* index, int nx)
{
int i;
short i0, i1, i2, i3;
short j0, j1, j2, j3;
double xi0, xi1, xi2, xi3;
double xj0, xj1, xj2, xj3;
short t;
int a, b, ia, ib, ibs;
int mask;
int nbits, nbot, ntop, ndiff, n2, halfn;
nbits = 0;
i = nx;
while (i > 1)
{
i = i >> 1;
nbits++;
}
nbot = nbits >> 1;
ndiff = nbits & 1;
ntop = nbot + ndiff;
n2 = 1 << ntop;
mask = n2 - 1;
halfn = nx >> 1;
for (i0 = 0; i0 < halfn; i0 += 2)
{
b = i0 & mask;
DSPF_sp_bitrev_cplx
DSPLIB Reference 4-7